48 results about "Local planning" patented technology

The invention relates to an air-ground collaborative exploration method in an unknown environment based on three-dimensional Gaussian splashing, and belongs to the field of air-ground robot collaborative exploration in a dangerous environment. The method comprises the following steps: S1, acquiring image data of a to-be-explored area by using an unmanned aerial vehicle, describing a complex scene and a differentiable rendering technology by using three-dimensional Gaussian distribution, accurately estimating a camera pose of the unmanned aerial vehicle and reconstructing a three-dimensional environment in real time by combining a simultaneous localization and mapping (SLAM) system, traversing a space and marking a series of key waypoints; step S2, the ground robot realizes accurate exploration of a local three-dimensional environment by using waypoints provided by the unmanned aerial vehicle and combining a collaborative mechanism of global planning and local planning; and S3, dynamically updating the path plan through the robot in the exploration process, and constructing a fine three-dimensional map of the exploration area. According to the invention, the air-ground robot can collaboratively explore the unknown environment and establish the environment map.

The invention discloses a complex environment-oriented body agent navigation and three-dimensional reconstruction method, and relates to the technical field of body agent navigation, and the method comprises the following steps: collecting environment data around a navigation body, using a fine-grained octree for close-range key areas (narrow slits and dead corners), adopting coarse voxel acceleration for a far area, and adopting coarse voxel acceleration for a near-range key area (narrow slits and dead corners); extracting large planes such as wall surfaces, beam columns and the like by using RANSAC (Random Sample Consensus), and constructing an environment'abstract skeleton 'for navigation reference; establishing a temporary three-dimensional space based on the point cloud of the whole body environment, dividing a plurality of detection planes in the space, performing position correction on an obstacle edge dot matrix in the detection planes, determining a movable range, and generating a safe motion path in a feasible space by applying a local planning algorithm; octree + differential coding is carried out on a local map, and only a current activity area and crisis point cloud are reserved; local full-stack deployment enables navigation to be free of dependence on remote communication, and sensing, mapping and navigation closed loop can still be completed when a link is broken.

The invention discloses a robot path planning method and device, equipment, a medium and a product, and relates to the field of robot obstacle avoidance, and the method comprises the steps: constructing a grid map of a target environment; according to the grid map, adopting an improved A * algorithm to obtain a global planning path; the improved A * algorithm constructs a dynamic heuristic function based on geometric distance and dynamic risk parameters on the basis of the A * algorithm; according to the global planning path, adopting a path decomposition method and an improved dynamic window algorithm to obtain a plurality of local planning paths; the improved dynamic window algorithm constructs an evaluation function based on a cross-modal fusion method and a collision time method on the basis of a dynamic window algorithm; and obtaining a robot path planning result according to all the local planning paths. According to the invention, the global path and local path planning of the robot is realized based on the improved A * algorithm and the improved dynamic window algorithm, the path planning efficiency and safety are improved, and the obstacle avoidance capability of the robot in a complex environment is enhanced.

The invention provides an unmanned aerial vehicle autonomous exploration method based on boundary detection and probability sampling fusion, and the method comprises the steps: firstly generating a high-quality viewpoint through a probability sampling model, and providing precise data support for path planning in an exploration stage; secondly, efficient collaboration of global planning and local planning is achieved by means of a layered planning architecture and a topological path search technology; and finally, through a re-planning mechanism, the robustness and task continuity of the unmanned aerial vehicle in the exploration process in a complex unknown environment are ensured. Aiming at the technical defects that the existing autonomous exploration method is easy to fall into local optimum, low in calculation efficiency, insufficient in track smoothness and the like, the invention provides a solution suitable for an unknown environment, and a space exploration task can be efficiently and quickly completed.

The invention relates to a self-balancing bicycle robot multi-task path planning method, which belongs to the technical field of mobile robot autonomous navigation, and comprises the following steps: constructing an environment grid model containing static obstacle information, and fusing obstacle repulsive force and a Voronoi diagram skeleton to guide and generate an environment safety potential field; receiving a multi-task target point sequence, and calculating an optimal cut-in course angle of each target point; performing global path search in a three-dimensional state space by adopting a forward-backward bimodal primitive to generate a global path meeting incomplete kinematics constraints; the local planning adopts an improved dynamic window algorithm, dynamic stability verification and pruning are carried out in the space of the linear speed and the front wheel steering angle, and an optimal instruction is selected. The technical problems of discontinuous path, dynamic instability, poor obstacle avoidance safety and the like during multi-task operation of the self-balancing bicycle robot are solved, and the operation safety, smoothness and efficiency of the robot in a complex unstructured environment are effectively and remarkably improved.

The invention discloses a multi-agent priority obstacle avoidance path planning method for a dynamic obstacle, and relates to the technical field of mobile agent path planning, the method comprises the following steps: a global planning stage: optimizing an A * algorithm by introducing a heuristic scaling factor, an obstacle and direction penalty term and a neighborhood adaptive extension mechanism, a path is smoothed by combining broken line reconstruction and a Bezier curve; in the local planning stage, the weight of a DWA evaluation function is dynamically adjusted through fuzzy control, and the real-time obstacle avoidance robustness is improved. Meanwhile, a priority obstacle avoidance strategy and a dynamic look-ahead mechanism are designed, multi-agent conflicts are coordinated, and collective stagnation is avoided. Simulation results show that the method shows better path length, search efficiency and obstacle avoidance performance in static, unknown static and dynamic obstacle environments, effectively improves the multi-agent coordination stability, and is suitable for actual scenes such as warehouse logistics and the like.

The invention belongs to the technical field of robots, and particularly relates to a robot local planning method and device, a computer readable storage medium and a robot. The method comprises the following steps: acquiring a local occupation grid map of the robot; generating point cloud data of the robot according to the local occupation grid map; wherein the point cloud data is an intersection point set of each ray taking the central position of the robot as a ray origin and an obstacle area in the locally occupied grid map; performing reinforcement learning training on a preset local planning network model based on the point cloud data to obtain a trained local planning network model; and performing local planning on the robot by using the trained local planning network model to obtain a local planning result of the robot. According to the method and the device, the local occupation grid map can be simplified and converted into the point cloud data, so that the point cloud data can be applied to reinforcement learning of local planning of the robot, and the performance of the local planning of the robot can be improved.

The invention belongs to the technical field of unmanned vehicle intelligent control, and particularly relates to a cooperative control method for unmanned information group dynamic interaction, and the method mainly relates to three main parts of sub-body information group initialization judgment, feature-based group global planning operation and feature-based group local planning operation. The method comprises the following steps: firstly, identifying and separating a daughter information group and extracting and calculating the daughter information group according to limited information which can be obtained by daughters in the group; according to the calculation result, the state of each daughter in the group in different environments can be effectively judged, so that the connection state between the daughters is obtained. On the basis of considering reasonable input and effective interaction of system information, the distance between different daughters is dynamically adjusted by taking group comprehensive performance as a target, so that the global and local planning operation and control process of the unmanned group overall architecture under the action of information interaction is realized.

The invention provides a hybrid local planning method and system based on a dynamic state diagram, and the method comprises the steps: calculating a displacement distance range and an orientation angle range of a target point based on the operation parameters, obtained in real time, of an autonomous mobile robot and a pre-constructed initial dynamic diagram; calculating state nodes based on the target point displacement distance range, the orientation angle range and the initial dynamic graph, and constructing a dynamic state graph through the state nodes; constructing a target path based on the dynamic state diagram and a preset search algorithm to obtain a target point, and obtaining a target linear speed and a target point orientation according to the target point and a preset speed strategy; obtaining a target angular velocity based on the target point and a preset path planning algorithm; and sending the target linear velocity, the target angular velocity and the target point orientation to the autonomous mobile robot, so that the autonomous mobile robot plans a local path. According to the method, the optimal path is dynamically and locally adjusted in real time under kinematics constraints, and the path planning reliability is improved.

In conventional robot navigation techniques learning and planning algorithms act independently without guiding each other simultaneously. A method and system for robotic navigation with simultaneous local path planning and learning is disclosed. The method discloses an approach to learn and plan simultaneously by assisting each other and improve the overall system performance. The planner acts as an actuator and helps to balance exploration and exploitation in the learning algorithm. The synergy between dynamic window approach (DWA) as a planning algorithm and a disclosed Next best Q-learning (NBQ) as a learning algorithm offers an efficient local planning algorithm. Unlike the traditional Q-learning, dimension of Q-tree in the NBQ is dynamic and does not require to define a priori.

The invention discloses a material carrying control method and device, a medium and a product, and relates to the technical field of multi-agent collaboration.The method comprises the steps that a global shortest path is determined through a double-layer FBS model self-closed-loop architecture; carrying materials from an initial position according to a global shortest path, and carrying out planned adjustment in real time in the carrying process to complete a global task target; wherein the planning adjustment process of the rescue material at any current position comprises the following steps: acquiring a local task target at the current position; determining a target planning algorithm at the current position based on the local task target at the current position by using a double-layer FBS model self-closed loop architecture; determining a local planning behavior at the current position according to a target planning algorithm at the current position by using a double-layer FBS model self-closed loop architecture; and carrying the relief goods at the current position based on the local planning behavior at the current position. According to the invention, material carrying control in a complex rescue scene can be realized.

The invention relates to an unmanned sweeper covering type sweeping operation method and system and a medium, and the method comprises the steps: M1, collecting the boundary of a to-be-swept area through a handheld positioning data collection device, importing the boundary into a cloud end, and enabling the precision of positioning data to reach the centimeter level; m2, a cloud global planning algorithm module reads vehicle end parameters and plans a coverage type global path through an algorithm in combination with region boundary information; and M3, the vehicle end local planning algorithm module receives the global path, intercepts the global path as a local planning path according to the current positioning, carries out longitudinal planning, generates a complete planning track, and issues the complete planning track to the control module. According to the method, the problems that an unmanned sweeping vehicle is difficult to realize coverage type sweeping operation and cannot adapt to a complex and changeable urban environment, and a traditional coverage type planning algorithm is long in time consumption are solved, and mutually restricted optimization dimensions such as obstacle avoidance, sweeping blind area elimination and operation efficiency improvement can be processed at the same time.

The invention provides a local planning method and device in wheel-foot robot navigation and electronic equipment. The method comprises the following steps: carrying out sparse processing on a plurality of global path points in navigation of the wheel-foot robot to obtain a plurality of inflection points and a final target point; when the wheel-foot robot reaches the current inflection point, the wheel-foot robot is switched into an in-situ stepping steering mode until the angle difference between the course angle of the wheel-foot robot at the current inflection point and the path direction of the connecting line from the current inflection point to the temporary target point is smaller than or equal to a target preset angle threshold value; the temporary target point is a next inflection point to be reached by the wheel-foot robot or a final target point; and switching to a linear rolling advancing mode until the first distance between the wheel-foot robot and the temporary target point is smaller than or equal to a target preset distance threshold value. When the wheel-foot robot reaches the final target point, the difference between the course angle of the wheel-foot robot and the course angle of the final target point is adjusted to be smaller than or equal to a target preset angle threshold value. Angular velocity and linear velocity decoupling of the wheel-foot robot is achieved, and calculation is simple.

This invention discloses a collaborative path planning method based on multi-constraint improved A* algorithm and a dynamic look-ahead mechanism. It constructs a feature distance field map containing a nonlinear safety potential field, transforming discrete environmental information into continuous safety gradients. An improved A* algorithm, incorporating dynamic adaptive heuristic weights, nonlinear safety potential field costs, and kinematic smoothness constraints, is used to plan the globally optimal path. A velocity-adaptive dynamic look-ahead mechanism is established to calculate dynamic look-ahead points that conform to the current motion state in real time. A multi-objective evaluation function containing a global traction index is introduced into the local planning process to optimize control commands by measuring the deviation between the local trajectory and the global intent. This invention effectively solves the problems of "wall-hugging effect," high computational cost in large-scale environments, and poor coordination between global and local planning in traditional methods, improving the navigation safety and smoothness of robots in complex unstructured scenarios.

The present application provides a space launch mission path planning method, device, electronic device and medium, the method comprising: extracting information from geographic information corresponding to the space launch mission and constructing a geographic topology relationship graph; splitting the geographic topology relationship graph according to the hierarchical relationship between different nodes to obtain multiple geographic topology relationship subgraphs; determining multiple candidate planning paths in each geographic topology relationship subgraph, and screening the multiple candidate planning paths based on the space launch mission performance parameters to determine the local planning path corresponding to the geographic topology relationship subgraph, connecting the first local planning path with the second local planning path to generate the best global planning path. By adopting the above-mentioned space launch mission path planning method, device, electronic device and medium, the problem of long search time of the path planning algorithm when the road network scale is large, the search space and the complexity of the space launch mission are high is solved.

This invention relates to a multi-task path planning method for a self-balancing bicycle robot, belonging to the field of autonomous navigation technology for mobile robots. The method includes: constructing an environmental grid model containing static obstacle information; fusing obstacle repulsion forces and a Venn diagram skeleton to guide the generation of a safe environmental potential field; receiving a sequence of multi-task target points and calculating the optimal heading angle for each target point; performing a global path search in a three-dimensional state space using forward-backward dual-modal primitives to generate a global path that satisfies nonholonomic kinematic constraints; and employing an improved dynamic window algorithm for local planning, performing dynamic stability verification and pruning within the space of linear velocity and front wheel steering angle to select the optimal instruction. This invention solves the technical problems of discontinuous paths, dynamic instability, and poor obstacle avoidance safety in multi-task operations of self-balancing bicycle robots, effectively and significantly improving the safety, smoothness, and efficiency of robot operations in complex unstructured environments.

Systems and methods for autonomous-vehicle navigation integrating path planning with a perception network. A Bird's Eye View costmap is generated at runtime using only onboard sensors. No external localization providers are used.

The present invention provides a method for local planning of a mobile robot in a crowd environment based on MPC dynamic game theory, comprising: establishing a dynamic game model under the MPC framework with the robot and surrounding pedestrians as participants; linearizing and approximating the dynamic game model to obtain an approximate dynamic game model, and solving the optimality conditions of the approximate model using the maximum principle; designing an inverse optimal control algorithm based on the optimality conditions, and using the inverse optimal control algorithm to identify weight parameters guiding pedestrian decision-making from real pedestrian trajectories; using the identified approximate dynamic game model as a local planner, combined with robot positioning and pedestrian detection algorithms, to achieve local planning and control of the robot in a dynamic crowd environment. This method enables the mobile robot to achieve excellent local planning and control effects in a dynamic crowd environment, such as quickly reaching the target point, avoiding pedestrians, and saving energy.

The present invention proposes an energy-saving path planning method for an AUV for water tunnel inspection. First, the tunnel inspection AUV is optimized and planned in a constructed environmental model. Then, a multi-attribute heuristic factor is added to the ant colony algorithm to plan the AUV path. Then, the speed of the AUV is planned to obtain a global path planning for the tunnel inspection AUV. Local dynamic planning is designed for the tunnel inspection AUV, and a method based on a two-layer planning framework is used to switch between global planning and local planning. The planned path and speed are obtained based on the global planning module and the local planning module, and the tunnel inspection AUV is subjected to fixed-depth energy-saving control. Energy-saving and control effects are taken into account in speed control and depth control, thereby completing the energy-saving path planning of the tunnel inspection AUV.

The invention discloses a cleaning robot path planning method based on adaptive partitioning and reinforcement learning, and belongs to the technical field of robots. According to the method, a double-layer planning framework is adopted, in a global planning layer, an adaptive tree partitioning algorithm (ATPA) is provided, working areas are dynamically divided according to environment layout, waste material distribution and robot load capacity, entrances and exits of all the areas are optimized, and macroscopic guidance is provided for local planning; in a local planning layer, an improved reinforcement learning algorithm based on a dominant actor-commentator (A2C) is provided, and a robot is guided to generate an ordered and smooth refined coverage path by designing a dual reward mechanism of'departing from a starting point 'and'linear motion'. According to the method, through the synergistic effect of global partition optimization and local strategy learning, the path length and the turning frequency are remarkably reduced, the path redundancy rate is minimized, multi-target collaborative optimization is achieved, and the overall efficiency and the intelligent level of cleaning operation are improved.

The application discloses a kind of intelligent vehicle local path planning method, device and storage medium, wherein method includes: according to positioning information and high-precision map information, the reference driving path required for intelligent car local path planning is obtained;According to the planning starting point of current planning frame is solved according to tracking effect;Smooth the reference driving path, obtain path frenet coordinate system according to the reference driving path after smoothing;Static obstacles and oncoming vehicles are projected to path frenet coordinate system, SL graph is generated, and path planning trajectory is obtained according to SL graph;Dynamic obstacle short-time prediction trajectory is projected to speed frenet coordinate system, ST graph is generated, and speed planning trajectory is obtained according to ST graph;Path planning trajectory and speed planning trajectory are coupled on natural coordinate system, and restore into high-dimensional local planning trajectory.The application uses SL graph and ST graph to process path and speed respectively, improves efficiency, and can be widely applied to trajectory planning technical field in unmanned driving.

This application provides a method and system for generating obstacle avoidance trajectories based on a diffusion strategy, relating to the field of intelligent control technology. The method acquires the operating status information, task target information, and environmental status information of a mobile robot; determines the local planning area requiring local obstacle avoidance planning; identifies obstacle occupancy information within the local planning area; determines the location and local deformation of facility boundaries within the local planning area; and determines the effective passage boundary. Starting from multiple initial noise sequences, it performs multi-step inverse diffusion denoising iterations under the constraints of guiding condition features to generate multiple candidate obstacle avoidance trajectories. Candidate obstacle avoidance trajectories that conflict with obstacle occupancy information, exceed the effective passage boundary, or do not meet execution constraints are eliminated, and the target obstacle avoidance trajectory is determined from the remaining candidate trajectories. This method can improve the safety and passage efficiency of local obstacle avoidance trajectories in operating environments where the boundaries of facilities on both sides of the passage may deform.

Embodiments of the present application provide a path planning method, device, automatic gardening equipment and computer program product. The path planning method comprises: receiving a preset walking direction of a working area; dividing the working area into a plurality of sub-areas; for each sub-area, determining an actual planning direction of the sub-area from the preset walking direction and a recommended planning direction of the sub-area, and determining a local planning path corresponding to the sub-area according to the actual planning direction, wherein the path length of the sub-area traversed along the recommended planning direction is the shortest; obtaining a moving sequence between the sub-areas; and determining a global planning path of the working area according to the local planning path of each sub-area and the moving sequence between the sub-areas. The method is more effective.

The invention belongs to the technical field of mobile robot path planning, and provides a global-local path planning method adaptive to fruit tree inter-row operation. According to the method, a dynamic weight mechanism is introduced into an A * algorithm in global path planning, and the weight of a heuristic function is adaptively adjusted according to two factors, namely the ratio of the distance from a node to a target point and the transverse spacing of fruit trees, so that the search precision is improved; a * algorithm is utilized to pre-plan and construct a real cost matrix which is used for guiding segmented optimization of the ant colony algorithm, meanwhile, an adaptive pheromone volatilization mechanism based on a solution improvement rate is adopted to improve convergence stability, and path smoothing is realized in combination with redundant point deletion. In local planning, a path deviation cost item is introduced into a dynamic window method to quantify trajectory deviation, and a dynamic weighting strategy is adopted to adaptively adjust the weight of each evaluation function according to the obstacle distance. According to the method, efficient, smooth and stable path planning can be realized in a complex orchard environment, and the method is suitable for a mobile robot for fruit tree row-to-row operation.

The invention provides a space-time tensor task priority local planning method for an unmanned surface vessel, and belongs to the technical field of autonomous unmanned system navigation and control, and the method comprises the steps: constructing a unified three-dimensional space-time tensor based on environment perception data; the three-dimensional space-time tensor performs integrated coding on the static obstacle information and the future prediction occupation information of the dynamic obstacle, and supports collision feasibility query of constant time complexity of any position and time combination; generating guidance reference information containing an expected course based on the time parameterization reference trajectory; generating a candidate control action set based on the current motion state, carrying out collision constraint verification on candidate control actions based on the three-dimensional space-time tensor, screening to obtain a safety action set meeting the requirement of no collision constraint, and taking the deviation between the minimum predicted ship course and the expected course as a unique optimization target in the safety action set. Selecting an optimal control action; and 4, generating a local planning path based on the optimal control action, and controlling the unmanned surface vessel to sail.

The invention discloses a multi-modal fusion tidal flat robot adaptive path planning method. The method comprises the following steps: (1) dynamic environment prediction; (2) multi-source data fusion; (3) path planning dynamic constraint adaptation; (4) performing global-local planning connection; according to the method, a data fusion module, an environment modeling module, a self-adaptive planning algorithm module and a path verification and adjustment module are arranged and are used for cooperative work to realize precise navigation of the tidal flat robot. The data fusion module serves as a core data support of the whole planning method and realizes multi-level fusion of ocean mode data, remote sensing inversion data and machine vision data; and the environment modeling module constructs a dynamic environment model based on the fused data, the dynamic environment model is divided into a global environment model and a local environment model, and combination of global overall planning and local fine perception is realized. Through deep fusion of an ocean mode, remote sensing inversion and machine vision, the limitation of traditional single data source path planning is broken through.

The application discloses a path planning method and device of a robot, the path planning method comprises the following steps: performing global path planning based on a path map in a moving range of the robot to obtain a global path of the robot from a current position to a target position; performing local path planning based on the global path and the current position of the robot to obtain a local path; recording information of the local path in the path map; and performing global path planning based on the path map after the information is recorded to update the global path. The application can solve the problem that the matching degree of the global planning path and the local planning path is too small in the prior art.

The invention provides a method for autonomously exploring in an indoor unknown environment for a mobile robot, the pose of the robot and an environment map are obtained through instant positioning and mapping, and a planning strategy of mutual switching of local exploration planning and global exploration planning is used. The robot generates candidate targets through random sampling in the local planning stage, the gain of the candidate targets is calculated, the optimal gain is obtained to serve as a local planning target point, and when no local boundary exists around the robot, the robot is switched to the global planning stage; in the global planning stage, the optimal global boundary point is used as an exploration target, after the robot reaches the target, the robot is switched into local exploration planning, and a new non-explored local area is searched again; when the robot does not have the global boundary, exploration is completed, and the robot returns to the initial position. Through mutual switching of local planning and global planning, the robot is guided to always explore an unknown area, and finally exploration traversal and mapping of the whole indoor area are completed.

The dammed lake capacity measurement underwater robot adaptive dynamic path planning method comprises the following steps: a shore-based system processes dammed lake images collected by a satellite subscription camera, obtains initial boundary longitude and latitude information of the dammed lake water area, and performs rasterization processing on the dammed lake water area map; after the underwater robot is launched, the shore-based system sends the divided dammed lake area boundary information and the starting position information to each underwater robot through a communication module; the underwater robot executes an initial area coverage path, a sensor carried by the underwater robot acquires real-time underwater robot bottom height information, a local planner adopts an adaptive dynamic form to calculate and obtain a new local path; according to the scanning width and the path length of the local planning path, combined with the average bottom height on the underwater robot motion path; the scanned area is compared with the initial area of the dammed lake to determine whether the underwater robot completes the area coverage scanning task.

The application provides a learning-based map-free autonomous navigation obstacle avoidance method, medium and equipment; wherein, the method is: reusable planning capability library is used to carry out map-free autonomous navigation obstacle avoidance for a mobile robot; the reusable planning capability library comprises a global planning module and a local planning module; the global planning module is used to guide the global navigation direction and generate ordered and discrete path points; the local planning module generates real-time actions based on a learning-based local navigation obstacle avoidance model; the mobile robot is controlled to move according to the actions generated by the local planning module, so as to navigate the mobile robot to each path point generated by the global planning in turn. The method combines global and local planning architectures, modularizes algorithm, adapts to different navigation tasks, avoids a large amount of retraining based on a deep reinforcement learning navigation method, and improves the generality and interpretability of the model.